[Feasibility of Adapting Various Tumor-to-normal Bone Ratio Images on an Automatic Quantification Package for Phantom-based Image Quality Assessment in Bone SPECT].

We investigated the impact of the tumor-to-normal bone ratio (TNR) on the concordance rate between a detectability score classified by software (DS_soft) using an automatic quantification package for bone SPECT (Hone Graph) and a detectability score classified by visual assessment (DS_visual), and considered the feasibility of applying this software to various TNR images. ^99mTc solution was filled into a SIM² bone phantom to achieve TNRs of 4, 6, and 8, performed by dynamic SPECT acquisitions performed for 12 minutes; reconstructions were performed using ordered subset expectation maximization at timepoints ranging from 4 to 12 minutes. This yielded a total of 384 lesions (96 SPECT images). We investigated the weighted kappa (κ_w) coefficient between DS_soft and DS_visual at various TNRs and evaluated the change in analysis accuracy before and after applying newly created analysis parameters. DSs were defined on a 4-point scale (4: excellent, 3: adequate, 2: average, 1: poor), and visual evaluations were conducted by three board-certified nuclear medicine technologists. The κ_w coefficients between DS_soft and DS_visual were 0.75, 0.97, and 0.93 for TNRs 4, 6, and 8, respectively, with each κ_w coefficient being significant (p<0.01). In the TNR 4 image group, κ_w coefficients significantly increased with the implementation of new parameters proposed in this study. We concluded that the software's automatic analysis would be closer to a visual assessment within the TNR range of 4-8 and that applying new parameters derived from this study to images with TNR 4 further improves the software's automatic analysis accuracy of DS_soft. We suggest that software will be a useful tool for optimizing bone SPECT imaging techniques.